PhotoHolmes: a Python library for forgery detection in digital images

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: O'Flaherty, Julián, Paganini, Rodrigo, Sotelo, Juan Pablo, Umpiérrez, Julieta, Gardella, Marina, Tailanian, Matías, Musé, Pablo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910752965656576
author O'Flaherty, Julián
Paganini, Rodrigo
Sotelo, Juan Pablo
Umpiérrez, Julieta
Gardella, Marina
Tailanian, Matías
Musé, Pablo
author_facet O'Flaherty, Julián
Paganini, Rodrigo
Sotelo, Juan Pablo
Umpiérrez, Julieta
Gardella, Marina
Tailanian, Matías
Musé, Pablo
contents In this paper, we introduce PhotoHolmes, an open-source Python library designed to easily run and benchmark forgery detection methods on digital images. The library includes implementations of popular and state-of-the-art methods, dataset integration tools, and evaluation metrics. Utilizing the Benchmark tool in PhotoHolmes, users can effortlessly compare various methods. This facilitates an accurate and reproducible comparison between their own methods and those in the existing literature. Furthermore, PhotoHolmes includes a command-line interface (CLI) to easily run the methods implemented in the library on any suspicious image. As such, image forgery methods become more accessible to the community. The library has been built with extensibility and modularity in mind, which makes adding new methods, datasets and metrics to the library a straightforward process. The source code is available at https://github.com/photoholmes/photoholmes.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14969
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PhotoHolmes: a Python library for forgery detection in digital images
O'Flaherty, Julián
Paganini, Rodrigo
Sotelo, Juan Pablo
Umpiérrez, Julieta
Gardella, Marina
Tailanian, Matías
Musé, Pablo
Computer Vision and Pattern Recognition
In this paper, we introduce PhotoHolmes, an open-source Python library designed to easily run and benchmark forgery detection methods on digital images. The library includes implementations of popular and state-of-the-art methods, dataset integration tools, and evaluation metrics. Utilizing the Benchmark tool in PhotoHolmes, users can effortlessly compare various methods. This facilitates an accurate and reproducible comparison between their own methods and those in the existing literature. Furthermore, PhotoHolmes includes a command-line interface (CLI) to easily run the methods implemented in the library on any suspicious image. As such, image forgery methods become more accessible to the community. The library has been built with extensibility and modularity in mind, which makes adding new methods, datasets and metrics to the library a straightforward process. The source code is available at https://github.com/photoholmes/photoholmes.
title PhotoHolmes: a Python library for forgery detection in digital images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.14969